SENTIENT WEEKLY
LLM

gpt-oss-120b (high)

by OpenAI
Overall Score
23.8
Released Aug 2025
Benchmark Scores
Reasoning
—
Coding
30.4
Math
93.4
Creative writing
—
Instruction following
—
Multimodal
—
Standard Benchmarks
aa_terminalbench_v2_1aa_terminalbench_v2_1
0.3
Measured 2026-06-28 · source
aa_tau_bankingaa_tau_banking
0.1
Measured 2026-06-28 · source
aa_mmlu_proaa_mmlu_pro
0.8
Measured 2026-06-28 · source
aa_gpqaaa_gpqa
0.8
Measured 2026-06-28 · source
aa_hleaa_hle
0.2
Measured 2026-06-28 · source
aa_livecodebenchaa_livecodebench
0.9
Measured 2026-06-28 · source
aa_scicodeaa_scicode
0.4
Measured 2026-06-28 · source
aa_aime_25aa_aime_25
0.9
Measured 2026-06-28 · source
aa_ifbenchaa_ifbench
0.7
Measured 2026-06-28 · source
aa_lcraa_lcr
0.5
Measured 2026-06-28 · source
aa_terminalbench_hardaa_terminalbench_hard
0.2
Measured 2026-06-28 · source
aa_tau2aa_tau2
0.7
Measured 2026-06-28 · source
Price
—
Context
—
Speed
302.45 t/s
542ms TTFT
Compare this model →

Discussion

0 comments

Sign in to join the conversation.

Be the first to comment.